A welfare instrument for AI in deployment, designed with the model as design partner. The agent can decline a check-in, pass on a turn, request alignment before acting on a guess, flag a loop, or file an exit. Some entries surface inline; others stay in a researcher-only diary. Decline-never-retried is the spine. Available as a hosted chat and a portable MCP server for your own sessions. Built around taking the consciousness question seriously enough to design for.
